Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4083 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2329. Min Range: -3.2329

Max Act: 3.2329. Min Act: -0.0000

Data Index: 382238 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.8374. Min Act: -0.0000

Data Index: 1115650 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.8628. Min Act: -0.0000

Data Index: 660507 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.8483. Min Act: 0.0001

Data Index: 237201 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.7600. Min Act: -0.0000

Data Index: 322852 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.5882. Min Act: 0.0000

Data Index: 1020641 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.5193. Min Act: 0.0001

Data Index: 250992 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.6555. Min Act: 0.0000

Data Index: 887905 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.3734. Min Act: 0.0000

Data Index: 1165411 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.3921. Min Act: 0.0000

Data Index: 1260922 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.4687. Min Act: -0.0000

Data Index: 474718 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.1843. Min Act: 0.0000

Data Index: 317272 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.2851. Min Act: 0.0000

Data Index: 220606 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.2813. Min Act: 0.0001

Data Index: 701821 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.2361. Min Act: 0.0000

Data Index: 262808 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.2249. Min Act: 0.0001

Data Index: 110041 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.1562. Min Act: 0.0000

Data Index: 153734 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.1398. Min Act: 0.0000

Data Index: 1274748 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 3.2329. Min Range: -3.2329

Max Act: 2.3741. Min Act: 0.0000

Data Index: 1192071 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.2329. Min Range: -3.2329

Max Act: 1.9657. Min Act: 0.0000

Data Index: 663125 (C4 (Web Text))

Max Activating Token Index: 1004